Sciweavers

3202 search results - page 500 / 641
» Memory access scheduling
Sort
View
IPPS
2008
IEEE
14 years 2 months ago
A Hybrid MPI design using SCTP and iWARP
Abstract— Remote Direct Memory Access (RDMA) and pointto-point network fabrics both have their own advantages. MPI middleware implementations typically use one or the other, howe...
Mike Tsai, Brad Penoff, Alan Wagner
ISLPED
2005
ACM
96views Hardware» more  ISLPED 2005»
14 years 1 months ago
Region-level approximate computation reuse for power reduction in multimedia applications
ABSTRACT Motivated by data value locality and quality tolerance present in multimedia applications, we propose a new micro-architecture, Region-level Approximate Computation Buffer...
Xueqi Cheng, Michael S. Hsiao
WDAG
2005
Springer
104views Algorithms» more  WDAG 2005»
14 years 1 months ago
Polymorphic Contention Management
Abstract. In software transactional memory (STM) systems, a contention manager resolves conflicts among transactions accessing the same memory locations. Whereas atomicity and ser...
Rachid Guerraoui, Maurice Herlihy, Bastian Pochon
SPAA
2004
ACM
14 years 1 months ago
Online algorithms for prefetching and caching on parallel disks
Parallel disks provide a cost effective way of speeding up I/Os in applications that work with large amounts of data. The main challenge is to achieve as much parallelism as poss...
Rahul Shah, Peter J. Varman, Jeffrey Scott Vitter
MICRO
2003
IEEE
116views Hardware» more  MICRO 2003»
14 years 1 months ago
Universal Mechanisms for Data-Parallel Architectures
Data-parallel programs are both growing in importance and increasing in diversity, resulting in specialized processors targeted at specific classes of these programs. This paper ...
Karthikeyan Sankaralingam, Stephen W. Keckler, Wil...